Promote Sign in Sign up

Catalogs

Models

800 matched .

Explore AI models for text, images, audio and coding. Filter by model task, open or closed weights, and Hugging Face availability.

Clear search and filters

All types Text · 2,080 Image · 398 Video · 224 Audio · 372 Coding · 40 Multimodal · 885 Structured data · 27 3D · 17
Weights and source · filters active
Open weights Closed On Hugging Face Clear filters
Most downloaded A–Z Recently synced
Explore other catalogs
Models Datasets Demos Devices Robots MCPs Papers Investors Fundraises Repositories News
How to choose models

Start with the task you need the model to perform, then narrow the model type and weight availability. Open weights do not automatically mean unrestricted commercial use. Check the original model card for the license, input requirements, evaluation results and hardware needs before choosing a model.

Understand our sources and data limits

  1. P Video Replace Pruna AI P-Video-Replace is Pruna AI’s video-replacement model for inserting referenced people into a source… Video · Closed Closed weights
  2. PaliGemma Google DeepMind PaliGemma is Google’s open vision-language model that accepts images plus text and outputs text for… Text · Closed Closed weights
  3. PaliGemma 2 Google DeepMind PaliGemma 2 is Google’s upgraded open vision-language model family based on Gemma 2, available in 3… Text · Closed Closed weights
  4. PaLM Google PaLM is Google’s Pathways Language Model, a large decoder-only Transformer built to scale across th… Text · Closed Closed weights
  5. PaLM 2 Google AI model by Google Text · Closed Closed weights
  6. PaLM-E Google AI model by Google Image · Closed Closed weights
  7. Palmyra X 004 WRITER Palmyra X 004 (X4) is Writer’s advanced enterprise LLM, part of the Palmyra X family. It’s tuned fo… Text · Closed Closed weights
  8. Palmyra X5 WRITER Palmyra X5 is Writer’s enterprise LLM built for multi-agent systems: a hybrid transformer with a 1M… Text · Closed Closed weights
  9. Pan-4B Pantograph Pan-4B is a 4 billion parameter goal-conditioned agent from Pantograph that plays Minecraft. It is… Multimodal · Closed Closed weights
  10. Paris Bagel LABS Paris by Bagel Labs is an open weight text to image diffusion model trained entirely through decent… Image · Closed Closed weights
  11. Parti Google AI model by Google Image · Closed Closed weights
  12. Phenaki Google Phenaki is a text-to-video model designed for long, story-like generations. It follows a sequence o… Video · Closed Closed weights
  13. Phoenix 1 Tavus Phoenix-1 is Tavus’ early Phoenix research model for realistic avatar generation, using 3D reconstr… Video · Closed Closed weights
  14. Phoenix 2 Tavus Phoenix-2 is Tavus’ next Phoenix research model that shifts the avatar rendering backbone toward 3D… Video · Closed Closed weights
  15. Phoenix 3 Tavus Phoenix-3 is Tavus’ full-face real-time rendering model for hyper-realistic conversational avatars… Multimodal · Closed Closed weights
  16. Phoenix 4 Tavus Phoenix-4 is Tavus’ real-time human rendering model that generates continuous facial behavior with… Multimodal · Closed Closed weights
  17. Phoenix-4.5 Tavus Phoenix-4.5 is Tavus's real-time human rendering model for AI video characters, generating full-fra… Video · Closed Closed weights
  18. Photon 1 Luma 1 Photon is Luma’s controllable text-to-image model for high-fidelity, photoreal results with solid… Image · Closed Closed weights
  19. Photon 1 (Induction Labs) Induction Labs Photon-1 is a sparse 106B-A5B mixture-of-experts imagination model trained on 18 years of computer… Video · Closed Closed weights
  20. Pi 0.7 Physical Intelligence π 0.7 is Physical Intelligence’s steerable general-purpose vision-language-action robot model. It i… Multimodal · Closed Closed weights
  21. Pika 1.0 Mellis AI model by Mellis Video · Closed Closed weights
  22. Pika 1.0 Mellis AI model by Mellis Video · Closed Closed weights
  23. Pika 1.5 Mellis AI model by Mellis Video · Closed Closed weights
  24. Pika 2.0 Mellis AI model by Mellis Video · Closed Closed weights
  25. Pika 2.1 Mellis AI model by Mellis Video · Closed Closed weights
  26. Pika 2.2 Mellis Text and image to video model with better motion control, identity consistency, and cleaner small d… Video · Closed Closed weights
  27. Pika 2.2 pikafrakes Mellis Frame consistency mode that emphasizes smooth motion and stable details over long clips. Video · Closed Closed weights
  28. Pika 2.2 Pikascenes Mellis Scene focused mode for multi shot sequences with consistent characters and look. Video · Closed Closed weights
  29. Pika 2.5 Mellis Pika 2.5 is an upgraded text and image to video model that delivers sharper detail, smoother motion… Video · Closed Closed weights
  30. Pika Music Mellis Generates original music from a text description, lyrics, a musical reference clip, and an optional… Audio · Closed Closed weights
  31. Pika pikadditions Mellis Add on effects and utilities for overlays, captions, and light post polish. Video · Closed Closed weights
  32. Pika SFX Mellis Generates sound effects from a text prompt. Produces short audio clips such as foley, ambient sound… Audio · Closed Closed weights
  33. Pika Soundtrack Mellis Generates a synchronized soundtrack for an uploaded video. Adds music, sound effects, or ambience t… Audio · Closed Closed weights
  34. Pika Speech Mellis Fast voice cloning text to speech model. Converts a written script into spoken audio using either a… Audio · Closed Closed weights
  35. PikaSteam 1 Mellis PikaStream 1.0 appears to be Pika’s real-time model for live video chat agents. Based on the post y… Multimodal · Closed Closed weights
  36. Pixel Perfect Depth Xiaomi Pixel-Perfect Depth is a monocular depth estimation model that uses pixel-space diffusion transform… Image · Closed Closed weights